Need of informatics in designing interoperable clinical registries

Majid Rastegar-Mojarad, Sunghwan Sohn, Liwei Wang, Feichen Shen, Troy C. Bleeker, William Arthur Cliby, Hongfang D Liu

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Clinical registries are designed to collect information relating to a particular condition for research or quality improvement. Intuitively, informatics in the area of data management and extraction plays a central role in clinical registries. Due to various reasons such as lack of informatics awareness or expertise, there may be little informatics involvement in designing clinical registries. In this paper, we studied a clinical registry from two critical perspectives, data quality and interoperability, where informatics can play a role. We evaluated these two aspects of an existing registry, Gynecology Surgery Registry, by mapping data elements and value sets, used in the registry, to a standardized terminology, SNOMED-CT. The results showed that majority of the values are ad-hoc and only 6 of 91 procedures in the registry could be mapped to the SNOMED-CT. To tackle this issue, we assessed the feasibility of automated data abstraction process, by training machine learning classifiers, based on existing manually extracted data. These classifiers achieved a reasonable average F-measure of 0.94. We concluded that more informatics engagement is needed to improve the interoperability, reusability, and quality of the registry.

Original languageEnglish (US)
Pages (from-to)78-84
Number of pages7
JournalInternational Journal of Medical Informatics
Volume108
DOIs
StatePublished - Dec 1 2017

Fingerprint

Informatics
Registries
Systematized Nomenclature of Medicine
Quality Improvement
Gynecology
Terminology

Keywords

  • Clinical registry
  • Informatics
  • Machine learning
  • Natural language processing

ASJC Scopus subject areas

  • Health Informatics

Cite this

Need of informatics in designing interoperable clinical registries. / Rastegar-Mojarad, Majid; Sohn, Sunghwan; Wang, Liwei; Shen, Feichen; Bleeker, Troy C.; Cliby, William Arthur; Liu, Hongfang D.

In: International Journal of Medical Informatics, Vol. 108, 01.12.2017, p. 78-84.

Research output: Contribution to journalArticle

@article{775bc8459e1841139ee3233cc1d3d5a6,
title = "Need of informatics in designing interoperable clinical registries",
abstract = "Clinical registries are designed to collect information relating to a particular condition for research or quality improvement. Intuitively, informatics in the area of data management and extraction plays a central role in clinical registries. Due to various reasons such as lack of informatics awareness or expertise, there may be little informatics involvement in designing clinical registries. In this paper, we studied a clinical registry from two critical perspectives, data quality and interoperability, where informatics can play a role. We evaluated these two aspects of an existing registry, Gynecology Surgery Registry, by mapping data elements and value sets, used in the registry, to a standardized terminology, SNOMED-CT. The results showed that majority of the values are ad-hoc and only 6 of 91 procedures in the registry could be mapped to the SNOMED-CT. To tackle this issue, we assessed the feasibility of automated data abstraction process, by training machine learning classifiers, based on existing manually extracted data. These classifiers achieved a reasonable average F-measure of 0.94. We concluded that more informatics engagement is needed to improve the interoperability, reusability, and quality of the registry.",
keywords = "Clinical registry, Informatics, Machine learning, Natural language processing",
author = "Majid Rastegar-Mojarad and Sunghwan Sohn and Liwei Wang and Feichen Shen and Bleeker, {Troy C.} and Cliby, {William Arthur} and Liu, {Hongfang D}",
year = "2017",
month = "12",
day = "1",
doi = "10.1016/j.ijmedinf.2017.10.004",
language = "English (US)",
volume = "108",
pages = "78--84",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Need of informatics in designing interoperable clinical registries

AU - Rastegar-Mojarad, Majid

AU - Sohn, Sunghwan

AU - Wang, Liwei

AU - Shen, Feichen

AU - Bleeker, Troy C.

AU - Cliby, William Arthur

AU - Liu, Hongfang D

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Clinical registries are designed to collect information relating to a particular condition for research or quality improvement. Intuitively, informatics in the area of data management and extraction plays a central role in clinical registries. Due to various reasons such as lack of informatics awareness or expertise, there may be little informatics involvement in designing clinical registries. In this paper, we studied a clinical registry from two critical perspectives, data quality and interoperability, where informatics can play a role. We evaluated these two aspects of an existing registry, Gynecology Surgery Registry, by mapping data elements and value sets, used in the registry, to a standardized terminology, SNOMED-CT. The results showed that majority of the values are ad-hoc and only 6 of 91 procedures in the registry could be mapped to the SNOMED-CT. To tackle this issue, we assessed the feasibility of automated data abstraction process, by training machine learning classifiers, based on existing manually extracted data. These classifiers achieved a reasonable average F-measure of 0.94. We concluded that more informatics engagement is needed to improve the interoperability, reusability, and quality of the registry.

AB - Clinical registries are designed to collect information relating to a particular condition for research or quality improvement. Intuitively, informatics in the area of data management and extraction plays a central role in clinical registries. Due to various reasons such as lack of informatics awareness or expertise, there may be little informatics involvement in designing clinical registries. In this paper, we studied a clinical registry from two critical perspectives, data quality and interoperability, where informatics can play a role. We evaluated these two aspects of an existing registry, Gynecology Surgery Registry, by mapping data elements and value sets, used in the registry, to a standardized terminology, SNOMED-CT. The results showed that majority of the values are ad-hoc and only 6 of 91 procedures in the registry could be mapped to the SNOMED-CT. To tackle this issue, we assessed the feasibility of automated data abstraction process, by training machine learning classifiers, based on existing manually extracted data. These classifiers achieved a reasonable average F-measure of 0.94. We concluded that more informatics engagement is needed to improve the interoperability, reusability, and quality of the registry.

KW - Clinical registry

KW - Informatics

KW - Machine learning

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=85030853243&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030853243&partnerID=8YFLogxK

U2 - 10.1016/j.ijmedinf.2017.10.004

DO - 10.1016/j.ijmedinf.2017.10.004

M3 - Article

C2 - 29132635

AN - SCOPUS:85030853243

VL - 108

SP - 78

EP - 84

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

ER -